Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 730 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 4.8023. Min Range: -4.8023

Max Act: 4.2924. Min Act: -0.0000

Data Index: 459282 (The Pile)

Max Activating Token Index: 907

Text #1

Max Range: 4.8023. Min Range: -4.8023

Max Act: 4.7454. Min Act: -0.0000

Data Index: 235231 (The Pile)

Max Activating Token Index: 189

Text #2

Max Range: 4.8023. Min Range: -4.8023

Max Act: 4.8023. Min Act: -0.0000

Data Index: 146507 (The Pile)

Max Activating Token Index: 591

Text #3

Max Range: 4.8023. Min Range: -4.8023

Max Act: 4.4284. Min Act: -0.0000

Data Index: 1759080 (The Pile)

Max Activating Token Index: 612

Text #4

Max Range: 4.8023. Min Range: -4.8023

Max Act: 4.3475. Min Act: -0.0000

Data Index: 1591582 (The Pile)

Max Activating Token Index: 106

Text #5

Max Range: 4.8023. Min Range: -4.8023

Max Act: 3.6867. Min Act: -0.0000

Data Index: 780635 (The Pile)

Max Activating Token Index: 926

Text #6

Max Range: 4.8023. Min Range: -4.8023

Max Act: 4.0108. Min Act: -0.0000

Data Index: 908459 (The Pile)

Max Activating Token Index: 21

Text #7

Max Range: 4.8023. Min Range: -4.8023

Max Act: 3.7997. Min Act: -0.0000

Data Index: 1353872 (The Pile)

Max Activating Token Index: 585

Text #8

Max Range: 4.8023. Min Range: -4.8023

Max Act: 3.7304. Min Act: -0.0000

Data Index: 860075 (The Pile)

Max Activating Token Index: 283

Text #9

Max Range: 4.8023. Min Range: -4.8023

Max Act: 3.6789. Min Act: -0.0000

Data Index: 415271 (The Pile)

Max Activating Token Index: 840

Text #10

Max Range: 4.8023. Min Range: -4.8023

Max Act: 3.9857. Min Act: -0.0000

Data Index: 924635 (The Pile)

Max Activating Token Index: 21

Text #11

Max Range: 4.8023. Min Range: -4.8023

Max Act: 3.6745. Min Act: -0.0000

Data Index: 1286062 (The Pile)

Max Activating Token Index: 48

Text #12

Max Range: 4.8023. Min Range: -4.8023

Max Act: 3.7695. Min Act: -0.0000

Data Index: 513437 (The Pile)

Max Activating Token Index: 431

Text #13

Max Range: 4.8023. Min Range: -4.8023

Max Act: 3.7694. Min Act: -0.0000

Data Index: 593064 (The Pile)

Max Activating Token Index: 546

Text #14

Max Range: 4.8023. Min Range: -4.8023

Max Act: 3.5931. Min Act: -0.0000

Data Index: 1421765 (The Pile)

Max Activating Token Index: 368

Text #15

Max Range: 4.8023. Min Range: -4.8023

Max Act: 3.7447. Min Act: -0.0000

Data Index: 1583795 (The Pile)

Max Activating Token Index: 773

Text #16

Max Range: 4.8023. Min Range: -4.8023

Max Act: 3.5447. Min Act: -0.0000

Data Index: 1128322 (The Pile)

Max Activating Token Index: 775

Text #17

Max Range: 4.8023. Min Range: -4.8023

Max Act: 3.3792. Min Act: -0.0000

Data Index: 1936843 (The Pile)

Max Activating Token Index: 68

Text #18

Max Range: 4.8023. Min Range: -4.8023

Max Act: 3.4861. Min Act: -0.0000

Data Index: 252299 (The Pile)

Max Activating Token Index: 918

Text #19

Max Range: 4.8023. Min Range: -4.8023

Max Act: 3.4734. Min Act: -0.0000

Data Index: 1151976 (The Pile)

Max Activating Token Index: 919